Granite 4.0 H Small
Available2025-09-22
32,000 tokens
Other 开发的 AI 模型,适合多种 AI 应用场景。
Supported modalities:TextCode
Quick Overview
Text Generation1/10
Code Generation1/10
Reasoning1/10
Multimodal1/10
Benchmark Results
Scores from leading benchmark suites.
10.8%
artificial-analysis-intelligence
8.5%
artificial-analysis-coding
13.7%
artificial-analysis-math
Performance Metrics
Latency and throughput performance.
1000ms
P50 Latency
447.093
tokens/sec
Dive Deeper
Explore detailed analyses by topic.
Pricing Info
Feature support
Streaming
Tool calling
JSON mode
